© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63080
    Prev
    Next
    INDEX
    Explanations

    code, questions and technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨåĪ«ä¸º
    -0.27
    åĪĨåĪ«
    -0.27
    _lot
    -0.26
    -packages
    -0.26
     polo
    -0.26
     petals
    -0.26
    /exec
    -0.26
     batter
    -0.26
    æĤłæĤł
    -0.25
     grapes
    -0.25
    POSITIVE LOGITS
    udi
    0.27
    ä»»ä½ķå½¢å¼ı
    0.26
    _FWD
    0.26
    ptr
    0.25
    aris
    0.24
     invented
    0.24
    æĢ§ä»·
    0.23
    .ud
    0.23
    bite
    0.23
    .rl
    0.23
    Activations Density 30.842%

    No Known Activations